Timezone: »
Poster
Kernel Alignment Risk Estimator: Risk Prediction from Training Data
Arthur Jacot · Berfin Simsek · Francesco Spadaro · Clement Hongler · Franck Gabriel
We study the risk (i.e. generalization error) of Kernel Ridge Regression (KRR) for a kernel $K$ with ridge $\lambda>0$ and i.i.d. observations. For this, we introduce two objects: the Signal Capture Threshold (SCT) and the Kernel Alignment Risk Estimator (KARE). The SCT $\vartheta_{K,\lambda}$ is a function of the data distribution: it can be used to identify the components of the data that the KRR predictor captures, and to approximate the (expected) KRR risk. This then leads to a KRR risk approximation by the KARE $\rho_{K, \lambda}$, an explicit function of the training data, agnostic of the true data distribution. We phrase the regression problem in a functional setting. The key results then follow from a finite-size adaptation of the resolvent method for general Wishart random matrices. Under a natural universality assumption (that the KRR moments depend asymptotically on the first two moments of the observations) we capture the mean and variance of the KRR predictor. We numerically investigate our findings on the Higgs and MNIST datasets for various classical kernels: the KARE gives an excellent approximation of the risk. This supports our universality hypothesis. Using the KARE, one can compare choices of Kernels and hyperparameters directly from the training set. The KARE thus provides a promising data-dependent procedure to select Kernels that generalize well.
Author Information
Arthur Jacot (EPFL)
Berfin Simsek (EPFL)
Francesco Spadaro (EPFL)
Clement Hongler (EPFL)
Franck Gabriel (EPFL)
More from the Same Authors
-
2022 Poster: Feature Learning in $L_2$-regularized DNNs: Attraction/Repulsion and Sparsity »
Arthur Jacot · Eugene Golikov · Clement Hongler · Franck Gabriel -
2021 Poster: DNN-based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel »
Benjamin Dupuis · Arthur Jacot -
2018 Poster: Neural Tangent Kernel: Convergence and Generalization in Neural Networks »
Arthur Jacot-Guillarmod · Clement Hongler · Franck Gabriel -
2018 Spotlight: Neural Tangent Kernel: Convergence and Generalization in Neural Networks »
Arthur Jacot-Guillarmod · Clement Hongler · Franck Gabriel